%A Chenyang Zhao, and Junling Wang %T Service Recommendation Model based on Rating Matrix and Context-Embedded LSTM %0 Journal Article %D 2019 %J Int J Performability Eng %R 10.23940/ijpe.19.09.p17.24322441 %P 2432-2441 %V 15 %N 9 %U {https://www.ijpe-online.com/CN/abstract/article_4232.shtml} %8 2019-09-30 %X Service recommendation based on deep learning has attracted more and more attention in recent years. However, most of the existing works do not make full use of contextual information when acquiring latent preference features of users. Therefore, a personalized service recommendation model based on rating matrix and context-embedded LSTM is proposed in this paper. In this model, for a given user, based on different rating contexts, the rating matrix is firstly improved to have embedded contextual information, and then a sequence of service vectors is obtained from the improved rating matrix according to the order in which the user consumes services. Motivated by the successful use of the LSTM network for processing sequential data, the sequence of service vectors is input into the LSTM network to obtain the preference features of the user. Based on the preference features of the user, the selection probability distribution of all candidate services is output by using a softmax network. Finally, Top-N services that the user may be most interested in are returned to the user. Experimental results demonstrate that the proposed model can achieve better performance than various competitive baseline methods.